© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 131759
    Prev
    Next
    INDEX
    Explanations

    internet calculators

    np_acts-logits-general · gemini-2.5-flash-lite

    sharing secrets and security information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵
    0.56
    n
    0.54
    I
    0.52
    g
    0.51
    stile
    0.51
    in
    0.47
    ং
    0.44
    У
    0.44
     देखिएगा
    0.44
     aggregate
    0.44
    POSITIVE LOGITS
     répondre
    0.54
     pequeñas
    0.53
    ſs
    0.52
     pomoći
    0.49
     dédié
    0.49
     différentes
    0.47
     publier
    0.47
     dansk
    0.46
     चलने
    0.46
    orschungs
    0.46
    Activations Density 0.001%

    No Known Activations